---
title: "Show or Tell? Modeling the evolution of request-making in"
description: "The authors propose ReCCRE, a scheme that labels every word of a user's first turn as one of four parts: the request itself… 44 references."
authors: ["Shengqi Zhu", "Jeffrey Rzeszotarski", "David Mimno"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.265/"
doi: "10.18653/v1/2026.findings-eacl.265"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhu-2026-show-or-tell-modeling-evolution/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhu-2026-show-or-tell-modeling-evolution/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/49/) / Show or Tell? Modeling the evolution of request-making in Human-LLM conversations

# Show or Tell? Modeling the evolution of request-making in Human-LLM conversations

**Authors:** Shengqi Zhu, Jeffrey Rzeszotarski and [David Mimno](https://md.research.elamur.ai/free/en/authors/david-mimno/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-eacl.265/) · [PDF](https://aclanthology.org/2026.findings-eacl.265.pdf) · [DOI 10.18653/v1/2026.findings-eacl.265](https://doi.org/10.18653/v1/2026.findings-eacl.265) · [OpenAlex](https://openalex.org/W7140115677)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Studies of real-world chatbot logs usually classify *what* people ask LLMs to do. This paper looks instead at *how* they phrase requests, a pattern that topic variety tends to obscure. The authors propose ReCCRE, a scheme that labels every word of a user's first turn as one of four parts: the request itself, supporting context (including pasted material to process), roles assigned to the model, or leftover task-independent expression templates. A semi-automatic annotation loop scales the scheme to WildChat. A strong proprietary model and a smaller local model label data in parallel, a human resolves their disagreements, and the local model eventually annotates the full corpus.

Compared with human-to-human requests in the Stanford Politeness Datasets, human-LLM requests form a distinct register. Over time, queries shift from bare requests toward requests with more context. Individual users try out different phrasings at first and then settle into more stable habits. The work matters for user studies, computational pragmatics, and alignment: separated components could support data augmentation and more robust evaluation.

## Key points
- Source corpus: 317,373 first-turn user inputs from WildChat. The released ReCCRE dataset contains 211,414 segmented utterances, restricted mainly to English-language logs.
- Annotators: gpt-4o-2024-08-06 served as the interim reference model and Qwen2.5-14B-Instruct as the full-scale annotator. Three review-and-revise rounds covered 762 instances, and agreement between the two models rose from 57% to 79% to 87%. Fewer than 0.5% of final outputs were badly formatted.
- Query types fall along a spectrum from request-centric patterns (e.g., single [R], [R][C]) to context-infused combinations. Some inputs are conversational and others are non-conversational.
- Diachronic analysis using simple off-the-shelf metrics (gte embeddings, Lexical Richness) shows that experienced users vary their expressions less and include more context.
- Data and code are available at github.com/CurlyZhu/ReCCRE. Stated limitations include reliance on WildChat alone, a fixed time window, and an English-only scope.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/) — University, Ithaca, United States · 134 works · 65,159 citations
- [Loyola University Maryland](https://md.research.elamur.ai/free/en/universities/loyola-university-maryland/) — University, Baltimore, United States · 2 works · 23 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Shengqi Zhu, Jeffrey Rzeszotarski and David Mimno. 2026. Show or Tell? Modeling the evolution of request-making in Human-LLM conversations. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhu2026show,
  title = {{Show or Tell? Modeling the evolution of request-making in Human-LLM conversations}},
  author = {Shengqi Zhu, Jeffrey Rzeszotarski and David Mimno},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.265},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.265}
}
```

- [← previous Shorten After You're Right: Lazy Length Penalties for Reasoning RL](https://md.research.elamur.ai/free/en/papers/yuan-2026-shorten-after-you-re-right/)
- [next → Shughni Machine Translation Enhanced by Donor Languages](https://md.research.elamur.ai/free/en/papers/novokshanov-2026-shughni-machine-translation-enhanced-donor/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/49/)

## References

44 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alan Chamberlain, Andy Crabtree, Tom Rodden, Matt Jones, and Yvonne Rogers. 2012. Research in the wild: understanding ‘in the wild’ approaches to design and development. In Proceedings of the designing interactive systems conference, pages 795–796. [find](https://scholar.google.com/scholar?q=Alan+Chamberlain%2C+Andy+Crabtree%2C+Tom+Rodden%2C+Matt+Jones%2C+and+Yvonne+Rogers%2E+2012%2E+Research+in+the+wild%3A+understanding+%E2%80%98in+the+wild%E2%80%99+approaches+to+design+and+development%2E+In+Proceedings+of+the+designin)
2. Jingwen Cheng, Kshitish Ghate, Wenyue Hua, William Yang Wang, Hong Shen, and Fei Fang. 2025. REALM: A dataset of real-world LLM use cases. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8331–8341, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jingwen+Cheng%2C+Kshitish+Ghate%2C+Wenyue+Hua%2C+William+Yang+Wang%2C+Hong+Shen%2C+and+Fei+Fang%2E+2025%2E+REALM%3A+A+dataset+of+real%2Dworld+LLM+use+cases%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)
3. Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael Jordan, Joseph E Gonzalez, and 1 others. 2024. [Chatbot arena: An open platform for evaluating llms by human preference](https://md.research.elamur.ai/free/en/papers/chiang-2024-chatbot-arena-open-platform-evaluating/). In Forty-first International Conference on Machin…
4. Alexander S. Choi, Syeda Sabrina Akter, JP Singh, and Antonios Anastasopoulos. 2024. The LLM effect: Are humans truly using LLMs, or are they being influenced by them instead? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22032–22054, Miami, Florida… [find](https://scholar.google.com/scholar?q=Alexander+S%2E+Choi%2C+Syeda+Sabrina+Akter%2C+JP+Singh%2C+and+Antonios+Anastasopoulos%2E+2024%2E+The+LLM+effect%3A+Are+humans+truly+using+LLMs%2C+or+are+they+being+influenced+by+them+instead%3F+In+Proceedings+of+the+20)
5. Saffron Huang, Esin Durmus, Miles McCain, Kunal Handa, Alex Tamkin, Jerry Hong, Michael Stern, Arushi Somani, Xiuruo Zhang, and Deep Ganguli. 2025. Values in the wild: Discovering and analyzing values in real-world language model interactions. arXiv preprint arXiv:2504.15236. — [arXiv:2504.15236](https://arxiv.org/abs/2504.15236) [find](https://scholar.google.com/scholar?q=Saffron+Huang%2C+Esin+Durmus%2C+Miles+McCain%2C+Kunal+Handa%2C+Alex+Tamkin%2C+Jerry+Hong%2C+Michael+Stern%2C+Arushi+Somani%2C+Xiuruo+Zhang%2C+and+Deep+Ganguli%2E+2025%2E+Values+in+the+wild%3A+Discovering+and+analyzing+values)
6. Michael A Covington and Joe D McFall. 2010. Cutting the gordian knot: The moving-average type–token ratio (mattr). Journal of quantitative linguistics, 17(2):94–100. [find](https://scholar.google.com/scholar?q=Michael+A+Covington+and+Joe+D+McFall%2E+2010%2E+Cutting+the+gordian+knot%3A+The+moving%2Daverage+type%E2%80%93token+ratio+%28mattr%29%2E+Journal+of+quantitative+linguistics%2C+17%282%29%3A94%E2%80%93100%2E)
7. Jonathan Ivey, Shivani Kumar, Jiayu Liu, Hua Shen, Sushrita Rakshit, Rohan Raju, Haotian Zhang, Aparna Ananthasubramaniam, Junghwan Kim, Bowen Yi, and 1 others. 2024. Real or robotic? assessing whether llms accurately simulate qualities of human responses in dialogue. arXiv preprint arXiv:2409.08330… — [arXiv:2409.08330](https://arxiv.org/abs/2409.08330) [find](https://scholar.google.com/scholar?q=Jonathan+Ivey%2C+Shivani+Kumar%2C+Jiayu+Liu%2C+Hua+Shen%2C+Sushrita+Rakshit%2C+Rohan+Raju%2C+Haotian+Zhang%2C+Aparna+Ananthasubramaniam%2C+Junghwan+Kim%2C+Bowen+Yi%2C+and+1+others%2E+2024%2E+Real+or+robotic%3F+assessing+whethe)
8. Cristian Danescu-Niculescu-Mizil, Moritz Sudhof, Dan Jurafsky, Jure Leskovec, and Christopher Potts. 2013. [A computational approach to politeness with application to social factors](https://md.research.elamur.ai/free/en/papers/mizil-2013-computational-approach-politeness-application-social/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pa…
9. Shachar Don-Yehiya, Leshem Choshen, and Omri Abend. 2024. Naturally occurring feedback is common, extractable and useful. arXiv preprint arXiv:2407.10944. — [arXiv:2407.10944](https://arxiv.org/abs/2407.10944) [find](https://scholar.google.com/scholar?q=Shachar+Don%2DYehiya%2C+Leshem+Choshen%2C+and+Omri+Abend%2E+2024%2E+Naturally+occurring+feedback+is+common%2C+extractable+and+useful%2E+arXiv+preprint+arXiv%3A2407%2E10944%2E+%E2%80%94+%5BarXiv%3A2407%2E10944%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F24)
10. Ge Gao, Alexey Taymanov, Eduardo Salinas, Paul Mineiro, and Dipendra Misra. 2024a. Aligning LLM agents by learning latent preference from user edits. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Ge+Gao%2C+Alexey+Taymanov%2C+Eduardo+Salinas%2C+Paul+Mineiro%2C+and+Dipendra+Misra%2E+2024a%2E+Aligning+LLM+agents+by+learning+latent+preference+from+user+edits%2E+In+The+Thirty%2Deighth+Annual+Conference+on+Neural+I)
11. Jie Gao, Simret Araya Gebreegziabher, Kenny Tsu Wei Choo, Toby Jia-Jun Li, Simon Tangi Perrault, and Thomas W Malone. 2024b. A taxonomy for human-llm interaction modes: An initial exploration. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA ’24, New York, NY… [find](https://scholar.google.com/scholar?q=Jie+Gao%2C+Simret+Araya+Gebreegziabher%2C+Kenny+Tsu+Wei+Choo%2C+Toby+Jia%2DJun+Li%2C+Simon+Tangi+Perrault%2C+and+Thomas+W+Malone%2E+2024b%2E+A+taxonomy+for+human%2Dllm+interaction+modes%3A+An+initial+exploration%2E+In+Exte)
12. Kunal Handa, Alex Tamkin, Miles McCain, Saffron Huang, Esin Durmus, Sarah Heck, Jared Mueller, Jerry Hong, Stuart Ritchie, Tim Belonax, and 1 others. 2025. Which economic tasks are performed with ai? evidence from millions of claude conversations. arXiv preprint arXiv:2503.04761. [find](https://scholar.google.com/scholar?q=Kunal+Handa%2C+Alex+Tamkin%2C+Miles+McCain%2C+Saffron+Huang%2C+Esin+Durmus%2C+Sarah+Heck%2C+Jared+Mueller%2C+Jerry+Hong%2C+Stuart+Ritchie%2C+Tim+Belonax%2C+and+1+others%2E+2025%2E+Which+economic+tasks+are+performed+with+ai%3F+)
13. Zeyu He, Saniya Naphade, and Ting-Hao Kenneth Huang. 2025. Prompting in the dark: Assessing human performance in prompt engineering for data labeling when gold labels are absent. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, CHI ’25, New York, NY, USA. Association… [find](https://scholar.google.com/scholar?q=Zeyu+He%2C+Saniya+Naphade%2C+and+Ting%2DHao+Kenneth+Huang%2E+2025%2E+Prompting+in+the+dark%3A+Assessing+human+performance+in+prompt+engineering+for+data+labeling+when+gold+labels+are+absent%2E+In+Proceedings+of+the)
14. Dun-Ming Huang, Pol Van Rijn, Ilia Sucholutsky, Raja Marjieh, and Nori Jacoby. 2024. Characterizing similarities and divergences in conversational tones in humans and LLMs by sampling with people. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: L… [find](https://scholar.google.com/scholar?q=Dun%2DMing+Huang%2C+Pol+Van+Rijn%2C+Ilia+Sucholutsky%2C+Raja+Marjieh%2C+and+Nori+Jacoby%2E+2024%2E+Characterizing+similarities+and+divergences+in+conversational+tones+in+humans+and+LLMs+by+sampling+with+people%2E+In+)
15. Zhihua Jin, Shiyi Liu, Haotian Li, Xun Zhao, and Huamin Qu. 2025. Jailbreakhunter: a visual analytics approach for jailbreak prompts discovery from large-scale human-llm conversational datasets. IEEE Transactions on Visualization and Computer Graphics. [find](https://scholar.google.com/scholar?q=Zhihua+Jin%2C+Shiyi+Liu%2C+Haotian+Li%2C+Xun+Zhao%2C+and+Huamin+Qu%2E+2025%2E+Jailbreakhunter%3A+a+visual+analytics+approach+for+jailbreak+prompts+discovery+from+large%2Dscale+human%2Dllm+conversational+datasets%2E+IEEE+)
16. Hannah Rose Kirk, Alexander Whitefield, Paul Rottger, Andrew M Bean, Katerina Margatina, Rafael Mosquera-Gomez, Juan Ciro, Max Bartolo, Adina Williams, He He, and 1 others. 2024. [The prism alignment dataset: What participatory, representative and individualised human feedback reveals about the subje…](https://md.research.elamur.ai/free/en/papers/kirk-2024-prism-alignment-dataset-participatory-representative/)
17. Steven Kolawole, Keshav Santhanam, Virginia Smith, and Pratiksha Thaker. 2025. Parallelprompt: Extracting parallelism from large language model queries. Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Datasets and Benchmarks Track. [find](https://scholar.google.com/scholar?q=Steven+Kolawole%2C+Keshav+Santhanam%2C+Virginia+Smith%2C+and+Pratiksha+Thaker%2E+2025%2E+Parallelprompt%3A+Extracting+parallelism+from+large+language+model+queries%2E+Proceedings+of+the+39th+Conference+on+Neural+In)
18. Batia Laufer and Paul Nation. 1995. Vocabulary size and use: Lexical richness in l2 written production. Applied linguistics, 16(3):307–322. [find](https://scholar.google.com/scholar?q=Batia+Laufer+and+Paul+Nation%2E+1995%2E+Vocabulary+size+and+use%3A+Lexical+richness+in+l2+written+production%2E+Applied+linguistics%2C+16%283%29%3A307%E2%80%93322%2E)
19. Dong-Ho Lee, Adyasha Maharana, Jay Pujara, Xiang Ren, and Francesco Barbieri. 2025. Realtalk: A 21-day real-world dataset for long-term conversation. arXiv preprint arXiv:2502.13270. — [arXiv:2502.13270](https://arxiv.org/abs/2502.13270) [find](https://scholar.google.com/scholar?q=Dong%2DHo+Lee%2C+Adyasha+Maharana%2C+Jay+Pujara%2C+Xiang+Ren%2C+and+Francesco+Barbieri%2E+2025%2E+Realtalk%3A+A+21%2Dday+real%2Dworld+dataset+for+long%2Dterm+conversation%2E+arXiv+preprint+arXiv%3A2502%2E13270%2E+%E2%80%94+%5BarXiv%3A2502%2E132)
20. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. [Towards general text embeddings with multi-stage contrastive learning](https://md.research.elamur.ai/free/en/papers/li-2023-towards-general-text-embeddings-multi/). arXiv preprint arXiv:2308.03281.
21. Tao Long, Sitong Wang, Émilie Fabre, Tony Wang, Anup Sathya, Jason Wu, Savvas Dimitrios Petridis, Ding Li, Tuhin Chakrabarty, Yue Jiang, and 1 others. 2025. Facilitating longitudinal interaction studies of ai systems. In Adjunct Proceedings of the 38th Annual ACM Symposium on User Interface Software… [find](https://scholar.google.com/scholar?q=Tao+Long%2C+Sitong+Wang%2C+%C3%89milie+Fabre%2C+Tony+Wang%2C+Anup+Sathya%2C+Jason+Wu%2C+Savvas+Dimitrios+Petridis%2C+Ding+Li%2C+Tuhin+Chakrabarty%2C+Yue+Jiang%2C+and+1+others%2E+2025%2E+Facilitating+longitudinal+interaction+studi)
22. Zilin Ma, Yiyang Mei, Krzysztof Z. Gajos, and Ian Arawjo. 2024. Schrödinger’s update: User perceptions of uncertainties in proprietary large language model updates. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA ’24, New York, NY, USA. Association for Compu… [find](https://scholar.google.com/scholar?q=Zilin+Ma%2C+Yiyang+Mei%2C+Krzysztof+Z%2E+Gajos%2C+and+Ian+Arawjo%2E+2024%2E+Schr%C3%B6dinger%E2%80%99s+update%3A+User+perceptions+of+uncertainties+in+proprietary+large+language+model+updates%2E+In+Extended+Abstracts+of+the+CHI+Co)
23. CHI Conference on Human Factors in Computing Systems, CHI ’25, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=CHI+Conference+on+Human+Factors+in+Computing+Systems%2C+CHI+%E2%80%9925%2C+New+York%2C+NY%2C+USA%2E+Association+for+Computing+Machinery%2E)
24. Atefeh Mahdavi Goloujeh, Anne Sullivan, and Brian Magerko. 2024. Is it AI or is it me? understanding users’ prompt journey with text-to-image generative ai tools. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI ’24, New York, NY, USA. Association for Computing Ma… [find](https://scholar.google.com/scholar?q=Atefeh+Mahdavi+Goloujeh%2C+Anne+Sullivan%2C+and+Brian+Magerko%2E+2024%2E+Is+it+AI+or+is+it+me%3F+understanding+users%E2%80%99+prompt+journey+with+text%2Dto%2Dimage+generative+ai+tools%2E+In+Proceedings+of+the+2024+CHI+Confer)
25. Lucas Shen. 2022. LexicalRichness: A small module to compute textual lexical richness. [find](https://scholar.google.com/scholar?q=Lucas+Shen%2E+2022%2E+LexicalRichness%3A+A+small+module+to+compute+textual+lexical+richness%2E)
26. Chaitanya Malaviya, Joseph Chee Chang, Dan Roth, Mohit Iyyer, Mark Yatskar, and Kyle Lo. 2025. Contextualized evaluations: Judging language model responses to underspecified queries. Transactions of the Association for Computational Linguistics, 13:878–900. [find](https://scholar.google.com/scholar?q=Chaitanya+Malaviya%2C+Joseph+Chee+Chang%2C+Dan+Roth%2C+Mohit+Iyyer%2C+Mark+Yatskar%2C+and+Kyle+Lo%2E+2025%2E+Contextualized+evaluations%3A+Judging+language+model+responses+to+underspecified+queries%2E+Transactions+of+t)
27. Philip M McCarthy. 2005. An assessment of the range and usefulness of lexical diversity measures and the potential of the measure of textual, lexical diversity (MTLD). Ph.D. thesis, The University of Memphis. [find](https://scholar.google.com/scholar?q=Philip+M+McCarthy%2E+2005%2E+An+assessment+of+the+range+and+usefulness+of+lexical+diversity+measures+and+the+potential+of+the+measure+of+textual%2C+lexical+diversity+%28MTLD%29%2E+Ph%2ED%2E+thesis%2C+The+University+of+)
28. Philip M McCarthy and Scott Jarvis. 2010. Mtld, vocd-d, and hd-d: A validation study of sophisticated approaches to lexical diversity assessment. Behavior research methods, 42(2):381–392. [find](https://scholar.google.com/scholar?q=Philip+M+McCarthy+and+Scott+Jarvis%2E+2010%2E+Mtld%2C+vocd%2Dd%2C+and+hd%2Dd%3A+A+validation+study+of+sophisticated+approaches+to+lexical+diversity+assessment%2E+Behavior+research+methods%2C+42%282%29%3A381%E2%80%93392%2E)
29. Niloofar Mireshghallah, Maria Antoniak, Yash More, Yejin Choi, and Golnoosh Farnadi. 2024. Trust no bot: Discovering personal disclosures in human-llm conversations in the wild. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Niloofar+Mireshghallah%2C+Maria+Antoniak%2C+Yash+More%2C+Yejin+Choi%2C+and+Golnoosh+Farnadi%2E+2024%2E+Trust+no+bot%3A+Discovering+personal+disclosures+in+human%2Dllm+conversations+in+the+wild%2E+In+First+Conference+on)
30. Kshitij Mishra, Mauajama Firdaus, and Asif Ekbal. 2022. Please be polite: Towards building a politeness adaptive dialogue system for goal-oriented conversations. Neurocomputing, 494:242–254. [find](https://scholar.google.com/scholar?q=Kshitij+Mishra%2C+Mauajama+Firdaus%2C+and+Asif+Ekbal%2E+2022%2E+Please+be+polite%3A+Towards+building+a+politeness+adaptive+dialogue+system+for+goal%2Doriented+conversations%2E+Neurocomputing%2C+494%3A242%E2%80%93254%2E)
31. Terran Mott, Aaron Fanganello, and Tom Williams. 2024. What a thing to say! which linguistic politeness strategies should robots use in noncompliance interactions? In Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, pages 501–510. [find](https://scholar.google.com/scholar?q=Terran+Mott%2C+Aaron+Fanganello%2C+and+Tom+Williams%2E+2024%2E+What+a+thing+to+say%21+which+linguistic+politeness+strategies+should+robots+use+in+noncompliance+interactions%3F+In+Proceedings+of+the+2024+ACM%2FIEEE+)
32. Sheshera Mysore, Debarati Das, Hancheng Cao, and Bahareh Sarrafzadeh. 2025. Prototypical human-AI collaboration behaviors from LLM-assisted writing in the wild. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 16819–16846, Suzhou, China. Association fo… [find](https://scholar.google.com/scholar?q=Sheshera+Mysore%2C+Debarati+Das%2C+Hancheng+Cao%2C+and+Bahareh+Sarrafzadeh%2E+2025%2E+Prototypical+human%2DAI+collaboration+behaviors+from+LLM%2Dassisted+writing+in+the+wild%2E+In+Proceedings+of+the+2025+Conference+o)
33. Alex Tamkin, Miles McCain, Kunal Handa, Esin Durmus, Liane Lovitt, Ankur Rathi, Saffron Huang, Alfred Mountfield, Jerry Hong, Stuart Ritchie, and 1 others. 2024. Clio: Privacy-preserving insights into real-world ai use. arXiv preprint arXiv:2412.13678. [find](https://scholar.google.com/scholar?q=Alex+Tamkin%2C+Miles+McCain%2C+Kunal+Handa%2C+Esin+Durmus%2C+Liane+Lovitt%2C+Ankur+Rathi%2C+Saffron+Huang%2C+Alfred+Mountfield%2C+Jerry+Hong%2C+Stuart+Ritchie%2C+and+1+others%2E+2024%2E+Clio%3A+Privacy%2Dpreserving+insights+into)
34. Xiaoyi Wang, Yuran Wang, and Xingyi Qiu. 2025. How to talk to ai: The role of preset prompt language styles in shaping conversational experience. International Journal of Human–Computer Interaction, 41(12):7763–7778. [find](https://scholar.google.com/scholar?q=Xiaoyi+Wang%2C+Yuran+Wang%2C+and+Xingyi+Qiu%2E+2025%2E+How+to+talk+to+ai%3A+The+role+of+preset+prompt+language+styles+in+shaping+conversational+experience%2E+International+Journal+of+Human%E2%80%93Computer+Interaction%2C+4)
35. Yingfan Wang, Haiyang Huang, Cynthia Rudin, and Yaron Shaposhnik. 2021. Understanding how dimension reduction tools work: An empirical approach to deciphering t-sne, umap, trimap, and pacmap for data visualization. Journal of Machine Learning Research, 22(201):1–73. [find](https://scholar.google.com/scholar?q=Yingfan+Wang%2C+Haiyang+Huang%2C+Cynthia+Rudin%2C+and+Yaron+Shaposhnik%2E+2021%2E+Understanding+how+dimension+reduction+tools+work%3A+An+empirical+approach+to+deciphering+t%2Dsne%2C+umap%2C+trimap%2C+and+pacmap+for+data+)
36. J.D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, and Qian Yang. 2023. Why johnny can’t prompt: How non-ai experts try (and fail) to design llm prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, CHI ’23, New York, NY, USA. Association for Computing Ma… [find](https://scholar.google.com/scholar?q=J%2ED%2E+Zamfirescu%2DPereira%2C+Richmond+Y%2E+Wong%2C+Bjoern+Hartmann%2C+and+Qian+Yang%2E+2023%2E+Why+johnny+can%E2%80%99t+prompt%3A+How+non%2Dai+experts+try+%28and+fail%29+to+design+llm+prompts%2E+In+Proceedings+of+the+2023+CHI+Confer)
37. Chao Zhang, Shengqi Zhu, Xinyu Yang, Yu-Chia Tseng, Shenrong Jiang, and Jeffrey M Rzeszotarski. 2025a. Navigating the fog: How university students recalibrate sensemaking practices to address plausible falsehoods in llm outputs. In Proceedings of the 7th ACM Conference on Conversational User Interfa… [find](https://scholar.google.com/scholar?q=Chao+Zhang%2C+Shengqi+Zhu%2C+Xinyu+Yang%2C+Yu%2DChia+Tseng%2C+Shenrong+Jiang%2C+and+Jeffrey+M+Rzeszotarski%2E+2025a%2E+Navigating+the+fog%3A+How+university+students+recalibrate+sensemaking+practices+to+address+plausibl)
38. Zhouqing Zhang, Kongmeng Liew, and Tham Pium-somboon. 2025b. What one million prompts tells us about ai usage, topics, and preferences. In 2025 IEEE Conference on Artificial Intelligence (CAI), pages 174–179. IEEE. [find](https://scholar.google.com/scholar?q=Zhouqing+Zhang%2C+Kongmeng+Liew%2C+and+Tham+Pium%2Dsomboon%2E+2025b%2E+What+one+million+prompts+tells+us+about+ai+usage%2C+topics%2C+and+preferences%2E+In+2025+IEEE+Conference+on+Artificial+Intelligence+%28CAI%29%2C+pages+)
39. Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, and Yuntian Deng. 2024. [Wildchat: 1m chatgpt interaction logs in the wild](https://md.research.elamur.ai/free/en/papers/zhao-2024-wildchat-1m-chatgpt-interaction-logs/). In The Twelfth International Conference on Learning Representations.
40. Rupak Sarkar, Bahareh Sarrafzadeh, Nirupama Chandrasekaran, Nagu Rangan, Philip Resnik, Longqi Yang, and Sujay Kumar Jauhar. 2025. Conversational user-ai intervention: A study on prompt rewriting for improved llm response generation. arXiv preprint arXiv:2503.16789. — [arXiv:2503.16789](https://arxiv.org/abs/2503.16789) [find](https://scholar.google.com/scholar?q=Rupak+Sarkar%2C+Bahareh+Sarrafzadeh%2C+Nirupama+Chandrasekaran%2C+Nagu+Rangan%2C+Philip+Resnik%2C+Longqi+Yang%2C+and+Sujay+Kumar+Jauhar%2E+2025%2E+Conversational+user%2Dai+intervention%3A+A+study+on+prompt+rewriting+for+)
41. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Tianle Li, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zhuohan Li, Zi Lin, Eric Xing, and 1 others. 2024a. [Lmsys-chat-1m: A large-scale real-world llm conversation dataset](https://md.research.elamur.ai/free/en/papers/zheng-2023-lmsys-chat-1m-large-scale/). In The Twelfth International Conference on Learning Representations.
42. Hope Schroeder, Marianne Aubin Le Quéré, Casey Randazzo, David Mimno, and Sarita Schoenebeck. 2025. Large language models in qualitative research: Uses, tensions, and intentions. In Proceedings of the 2025 [find](https://scholar.google.com/scholar?q=Hope+Schroeder%2C+Marianne+Aubin+Le+Qu%C3%A9r%C3%A9%2C+Casey+Randazzo%2C+David+Mimno%2C+and+Sarita+Schoenebeck%2E+2025%2E+Large+language+models+in+qualitative+research%3A+Uses%2C+tensions%2C+and+intentions%2E+In+Proceedings+of+the)
43. Mingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran, Moontae Lee, and David Jurgens. 2024b. When “a helpful assistant” is not really helpful: Personas in system prompts do not improve performances of large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages… [find](https://scholar.google.com/scholar?q=Mingqian+Zheng%2C+Jiaxin+Pei%2C+Lajanugen+Logeswaran%2C+Moontae+Lee%2C+and+David+Jurgens%2E+2024b%2E+When+%E2%80%9Ca+helpful+assistant%E2%80%9D+is+not+really+helpful%3A+Personas+in+system+prompts+do+not+improve+performances+of+lar)
44. Shengqi Zhu, Jeffrey M. Rzeszotarski, and David Mimno. 2025. Data paradigms in the era of llms: On the opportunities and challenges of qualitative data in the wild. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA ’25, New York, NY, USA. As… [find](https://scholar.google.com/scholar?q=Shengqi+Zhu%2C+Jeffrey+M%2E+Rzeszotarski%2C+and+David+Mimno%2E+2025%2E+Data+paradigms+in+the+era+of+llms%3A+On+the+opportunities+and+challenges+of+qualitative+data+in+the+wild%2E+In+Proceedings+of+the+Extended+Abst)

*Updated 2 November 2026*